Papers › Rethinking Complex Neural Network Architectures for Document Classification

Rethinking Complex Neural Network Architectures for Document Classification

1 Jun 2019NAACL 2019 6archive 2025-07-28

Ashutosh Adhikari, Achyudh Ram, Raphael Tang, Jimmy Lin

Neural network models for many NLP tasks have grown increasingly complex in recent years, making training and deployment more difficult. A number of recent papers have questioned the necessity of such architectures and found that well-executed, simpler models are quite effective. We show that this is also the case for document classification: in a large-scale reproducibility study of several recent neural models, we find that a simple BiLSTM architecture with appropriate regularization yields accuracy and F1 that are either competitive or exceed the state of the art on four standard benchmark datasets. Surprisingly, our simple model is able to achieve these results without attention mechanisms. While these regularization techniques, borrowed from language modeling, are not novel, to our knowledge we are the first to apply them in this context. Our work provides an open-source platform and the foundation for future work in document classification.

PaperPDFCode

Code

castorini/hedwig pytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ClassificationDocument ClassificationGeneral ClassificationLanguage ModelingLanguage Modelling

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Document Classification IMDb-M LSTM-reg (single model) Accuracy 52.8 #2 of 2 Archive leaderboard report
Document Classification Reuters-21578 LSTM-reg (single model) F1 87.0 #7 of 8 Archive leaderboard report
Text Classification Yelp-5 LSTM-reg (single moedl) Accuracy 68.7% #5 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

BiLSTMLSTMSigmoid ActivationTanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections